request+正则爬猫眼电影榜top100

import requests#d导入requests模块
from multiprocessing import Pool#进程池
from requests.exceptions import RequestException#用于异常处理
import json
import re#导入正则表达式

headers={
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.75 Safari/537.36'
}
def get_one_page(url):#请求单页内容的方法
    try:
        response = requests.get(url,headers=headers)#用requests.get请求url
        if response.status_code == 200:#判断，如果请求到的状态码==200（请求成功）
            return response.text#返回网页内容
        return None#如果是其他状态码返回None
    except RequestException:
        return None

def parse_one_page(html):#解析单页内容
    pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?src="(.*?)".*?name"><a'+'.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>'
                         +'.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>',re.S)#编写正则表达式
    items = re.findall(pattern,html)#应用已编好的正则表达式
    for item in items:#遍历
        yield {
            '排名':item[0],
            '图片地址': item[1],
            '标题': item[2],
            '主演': item[3].strip()[3:],
            '上映时间': item[4].strip()[5:],
            '评分': item[5]+item[6]
        }

def write_to_file(content):#将爬取结果保存到resuli.txt
    with open('result.txt','a',encoding='utf-8') as f:
        f.write(json.dumps(content,ensure_ascii=False)+'\n')
        f.close()

def main(offset):
    url = 'http://maoyan.com/board/4?offset='+str(offset)
    html = get_one_page(url)
    for item in parse_one_page(html):
        print(item)
        write_to_file(item)

if __name__=="__main__":
    pool = Pool()#构造进程池
    pool.map(main,[i*10 for i in range(10)])#爬取多页

标签：__,get,url,request,item,正则,requests,top100,page
来源： https://www.cnblogs.com/liunaiming/p/12234895.html